no explicit clear of each level when removing document

* keep the levels as they were, so any concurrent search
  operation getting a reference to this docid can follow
  old links and avoid getting trapped if possible
* ensure later GC can pick up any referenced data in
  HnswGraph::remove_node_for_document instead, it is
  more robust to have it in the graph layer anyway.

2 files changed, 8 insertions, 3 deletions

diff --git a/searchlib/src/vespa/searchlib/tensor/hnsw_graph.cpp b/searchlib/src/vespa/searchlib/tensor/hnsw_graph.cpp
index 69a1fbf2065..e47d1d8a48e 100644
--- a/searchlib/src/vespa/searchlib/tensor/hnsw_graph.cpp
+++ b/searchlib/src/vespa/searchlib/tensor/hnsw_graph.cpp
@@ -37,9 +37,16 @@ void
 HnswGraph::remove_node_for_document(uint32_t docid)
 {
     auto node_ref = node_refs[docid].load_acquire();
-    nodes.remove(node_ref);
+    assert(node_ref.valid());
+    auto levels = nodes.get(node_ref);
     vespalib::datastore::EntryRef invalid;
     node_refs[docid].store_release(invalid);
+    // Ensure data referenced through the old ref can be recycled:
+    nodes.remove(node_ref);
+    for (size_t i = 0; i < levels.size(); ++i) {
+        auto old_links_ref = levels[i].load_acquire();
+        links.remove(old_links_ref);
+    }
 }
 
 void     
diff --git a/searchlib/src/vespa/searchlib/tensor/hnsw_index.cpp b/searchlib/src/vespa/searchlib/tensor/hnsw_index.cpp
index 9382fef13f6..7d800be428e 100644
--- a/searchlib/src/vespa/searchlib/tensor/hnsw_index.cpp
+++ b/searchlib/src/vespa/searchlib/tensor/hnsw_index.cpp
@@ -400,7 +400,6 @@ void
 HnswIndex::remove_document(uint32_t docid)
 {
     bool need_new_entrypoint = (docid == get_entry_docid());
-    LinkArray empty;
     LevelArrayRef node_levels = _graph.get_level_array(docid);
     for (int level = node_levels.size(); level-- > 0; ) {
         LinkArrayRef my_links = _graph.get_link_array(docid, level);
@@ -413,7 +412,6 @@ HnswIndex::remove_document(uint32_t docid)
             remove_link_to(neighbor_id, docid, level);
         }
         mutual_reconnect(my_links, level);
-        _graph.set_link_array(docid, level, empty);
     }
     if (need_new_entrypoint) {
         HnswGraph::EntryNode entry;